Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral disclosure burden, and it does so reasonably well: it states that the tool writes a portable ZIP to a local directory and that raw disclosure payloads are excluded by default. It could add side-effect details (e.g., whether existing files are overwritten or whether the directory must be configured), but the core behavior is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences lead with the primary action and destination, then add the key default behavior. Every phrase carries information, with no filler or repetition of schema fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter download tool with an output schema present, the description covers the essential aspects: what is downloaded, where it goes, and a key default. It does not explain the full contents of the ZIP or prerequisites like a pre-configured directory, but these are minor given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It implicitly explains include_payloads via 'Raw disclosure payloads are excluded by default' but never explicitly names or maps either parameter. The decision_id is self-explanatory from the schema, and the boolean's default behavior is partially clarified, but the compensation is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Download') and identifies the concrete resource ('a portable LoopGrid evidence ZIP for a decision') plus the destination ('the configured local evidence directory'). This clearly distinguishes the tool from the record_* and verify_evidence siblings, which are different verbs and resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to choose this tool over the sibling tools or when not to use it. The phrase 'for a decision' gives minimal context, but no alternatives, exclusions, or prerequisites are mentioned, leaving the agent to infer when downloading is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavior itself. It does clarify a key behavior: this tool does NOT call Stripe, Salesforce, ServiceNow, or other business systems; it only records supplied evidence. However, it does not address side effects, idempotency, auth requirements, or failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that front-loads the core purpose and then adds a valuable exclusion note. There is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is too thin for a tool with five parameters, zero schema coverage, and no annotations. An agent would not know how to fill required fields like decision_id/tool or understand the purpose of optional fields. The output schema helps with return shape, but invocation guidance is still largely missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden of explaining parameters, but it mentions none of the five parameters. It does not clarify what tool, details, actor_id, decision_id, or external_reference mean or how they relate to the recording action.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool records evidence that an external tool/action executed, which is a specific verb+resource pairing. It also distinguishes itself from tools that would actually invoke business systems, though it does not explicitly differentiate from sibling record_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus the sibling tools like record_decision, record_review, or record_outcome. It implies usage for logging execution evidence but does not state conditions, alternatives, or exclusions beyond not calling external systems.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses the essential side-effect boundary: recording evidence only, never executing the proposed action, and optionally recording model output or evaluating a policy. It does not mention persistence confirmation, authority requirements, idempotency, or privacy-mode effects, which is a gap for a write-oriented tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences front-load the core purpose, add optional capabilities, and then give a crucial behavioral guardrail. Every sentence earns its place; there is no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high parameter count, nested objects, absence of annotations, and the surrounding sibling set, the description is too thin to fully orient an agent. It covers purpose and one exclusions, but it does not differentiate from record_review/record_outcome by name and provides almost no field-level guidance; the output schema only reduces the return-value burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are 14 parameters, so the description must compensate, but it only hints at model_output and policy_id. Required fields like decision_type and proposed_action, plus important optional fields such as authority, privacy_mode, and idempotency_key, are left entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States an explicit action and resource: 'Capture a consequential AI/agent decision in LoopGrid.' It also distinguishes itself from execution tools by noting 'This records evidence only and does not execute the proposed action,' which separates it from the sibling record_action. The purpose is specific and readily actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear behavioral context: use this to record decisions as evidence and optionally attach model output or evaluate a policy. It also provides a key exclusion—'does not execute the proposed action'—which prevents misuse as an action-execution tool. However, it does not explicitly name alternatives like record_review or record_outcome.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It explains that the integration is responsible for obtaining the outcome, but does not disclose side effects, required permissions, idempotency, error behavior, or what occurs on repeated calls. This is insufficient for a state-changing record operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with the core action and resource, then a key responsibility note. No wasted words or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters, 0% schema description coverage, and no annotations, the description leaves major gaps: status format, required parameter semantics, and tool behavior. The output schema exists but does not compensate for lack of parameter guidance. This is inadequate for correct autonomous invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only implies the meaning of decision_id and verified_against through the phrase 'for a decision after execution evidence exists,' but it gives no details on status values, details structure, actor_id, or external_reference. Parameters remain largely under-explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb 'Record' with a well-defined resource: an 'observed downstream outcome for a decision after execution evidence exists.' It distinguishes this tool from siblings like record_decision, record_review, and record_action by emphasizing downstream outcomes and evidence-based timing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear usage condition: use it 'after execution evidence exists' and when the integration has obtained an outcome from the real downstream system. It does not explicitly discuss exclusions or compare to sibling tools, but the timing and responsibility guidance are useful context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral disclosure burden. It openly states the tool is disabled by default, requires operator configuration of reviewer identity, and should be gated by human confirmation from the MCP host. This is meaningful auth/confirmation context beyond a naive read of the schema, though it doesn't detail what happens to the decision or whether the review is immutable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences front-load purpose and then deliver the key operational caveat. No filler or restatement of schema fields; each clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter tool with an output schema and no annotations, the description covers the purpose and prerequisites well but leaves out parameter roles and relationship to sibling record_* tools. It is adequate as an overview yet incomplete for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only mirrors the action enum in prose ("approve/reject") and never explains decision_id or reason. An agent gets no added meaning for two of the three parameters, leaving a clear gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: "Record a human approve/reject review in LoopGrid." It identifies this tool as recording human review decisions, which is clear. It doesn't explicitly contrast with the sibling record_decision/record_action/record_outcome tools, but the "review" scope is distinguishable enough to avoid deep confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for when the tool applies — when a human approve/reject review needs to be recorded — and adds operational prerequisites: disabled by default and requires operator enablement/configuration. It doesn't name alternatives or exclusion conditions, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'verify' without stating whether the operation is read-only, if it has side effects, what happens on failure, or what the output looks like. This is minimal behavioral transparency for a tool with no annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences. The first sentence states the primary purpose, and the second provides a clear alternative. No wasted words, and the main action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema, the description covers the basic purpose and an alternative, but it lacks behavioral details like what verification entails, what the response indicates, and any prerequisites. With no annotations and no parameter descriptions, it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not mention the parameter 'decision_id' at all, and the schema has no descriptions (coverage 0%). The description adds no meaning beyond the schema's bare parameter name, which is insufficient given the low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to verify the decision's signed workspace chain via the connected LoopGrid service. It is specific (verb 'verify' + resource 'signed workspace chain') and differentiates from the standalone verifier, which is a separate offline tool. It also naturally distinguishes from sibling recording tools by being a verification action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides an alternative usage: for independent offline verification of an exported ZIP, use the standalone LoopGrid verifier. This implies the current tool is for online, connected verification. It doesn't explicitly address when to use sibling tools, but those are clearly different (recording actions), so the usage context is reasonably clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.